Audio-Text-to-Text
Transformers
Safetensors
English
musicflamingo
text2text-generation
audio
speech
sound
music
reasoning
audio understanding
audio captioning
long-context
long-form-captioning
audio-language-model
long-audio
timestamp-grounding
Instructions to use nvidia/audio-flamingo-next-captioner-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/audio-flamingo-next-captioner-hf with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("nvidia/audio-flamingo-next-captioner-hf") model = AutoModelForSeq2SeqLM.from_pretrained("nvidia/audio-flamingo-next-captioner-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 61c412de025869a66b5829af3d9f6de3ec2e62390e981a19072aa2947aa8477f
- Size of remote file:
- 11.4 MB
- SHA256:
- a64cc913679c6eaf01ba137504e15a55d174d590944fe06f7b3899b2ae82de31
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.